commit c912f43eb6f7e97ff6aee800ef64949f69460c6c Author: ModelHub XC Date: Wed May 27 00:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ba39223 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PocketThinker-QwQ-3B-Instruct.IQ4_XS.gguf b/PocketThinker-QwQ-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..d4c1ac4 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5724da8511b1fc7ddc48a80b3132197e30adbdbd302089292494c4182fe4d73 +size 1753184672 diff --git a/PocketThinker-QwQ-3B-Instruct.Q2_K.gguf b/PocketThinker-QwQ-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..d28d8de --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:670101c2edb818a2df5a359e7884a6712776cbdc20d113bb1e118aa4baed9252 +size 1274755488 diff --git a/PocketThinker-QwQ-3B-Instruct.Q3_K_L.gguf b/PocketThinker-QwQ-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..56f5e49 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e380f491eb4b95df1e798e5493be01acf5fd043c395e5db74956107997da28b8 +size 1707391392 diff --git a/PocketThinker-QwQ-3B-Instruct.Q3_K_M.gguf b/PocketThinker-QwQ-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..0404882 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8626b784514a534dc328abd3f1fcb4ea0cf216341ab2d140805633784f89933a +size 1590475168 diff --git a/PocketThinker-QwQ-3B-Instruct.Q3_K_S.gguf b/PocketThinker-QwQ-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..baf4348 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ad82a45d7ab982d2c0b361846c432e0d9426d7050f960a6ffa3f2944f663085 +size 1454356896 diff --git a/PocketThinker-QwQ-3B-Instruct.Q4_K_M.gguf b/PocketThinker-QwQ-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..b716a02 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66fcb5c26956fc7f0b3526e0520fa31ea452c5c24c41e5efd784b228d33e77d7 +size 1929902496 diff --git a/PocketThinker-QwQ-3B-Instruct.Q4_K_S.gguf b/PocketThinker-QwQ-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..c88dc64 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bc636b8a93a50ed4149ce5b2e66fe99b85db02cf0b154347fa794354f489c6d +size 1834383776 diff --git a/PocketThinker-QwQ-3B-Instruct.Q5_K_M.gguf b/PocketThinker-QwQ-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..36a57e4 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7a062a11310167b9269d4ae2c6a95db7ee83bdcf0c62530da8347b832a51007 +size 2224814496 diff --git a/PocketThinker-QwQ-3B-Instruct.Q5_K_S.gguf b/PocketThinker-QwQ-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..d19401f --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7146814a436c535c91ddecd1d6249e6d29d2a928500ece63bc3d678ec7622cec +size 2169665952 diff --git a/PocketThinker-QwQ-3B-Instruct.Q6_K.gguf b/PocketThinker-QwQ-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..13b5cf1 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a8dac62976810a93eadb43e239d6540f1256a883ed84d1556d4d24a1aaf7fd +size 2538158496 diff --git a/PocketThinker-QwQ-3B-Instruct.Q8_0.gguf b/PocketThinker-QwQ-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..a2c5110 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba2ad5912da8b1fdf7712bd41ef264b611a5030b1b6cfd965f25dc6e87d50e63 +size 3285475744 diff --git a/PocketThinker-QwQ-3B-Instruct.f16.gguf b/PocketThinker-QwQ-3B-Instruct.f16.gguf new file mode 100644 index 0000000..33158eb --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1563995d3f4f0e0bd71e2e3962e2788caaa811ff3828de08ac8a748715b0854 +size 6178316704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8598767 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: prithivMLmods/PocketThinker-QwQ-3B-Instruct +datasets: +- amphora/QwQ-LongCoT-130K +- amphora/QwQ-LongCoT-130K-2 +- amphora/verfiable-25k +- amphora/m-math500 +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Math +- Code +- Thinker +- Reasoning +- 3B +- QwQ +- Mini +- text-generation-inference +- SFT +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/PocketThinker-QwQ-3B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PocketThinker-QwQ-3B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.f16.gguf) | f16 | 6.3 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +